Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quantities and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ').
    0.21
    ,—
    0.20
    ப்பட்டது
    0.20
    睐
    0.20
    沍
    0.19
    হাওয়া
    0.19
     ())
    0.18
     czyli
    0.18
     biocompat
    0.18
     నొప్పి
    0.18
    POSITIVE LOGITS
    5
    0.31
    3
    0.30
    4
    0.27
    8
    0.26
     million
    0.26
     percentage
    0.26
     percent
    0.25
    1
    0.25
    percent
    0.24
    percentage
    0.24
    Act Density 0.144%

    No Known Activations